PCA

gistfile1.py

def PCA(data,ncomps=2):
    """Perfrom a principle component analysis.

Parameters
----------
data : array
(n_vars, n_obs) array where `n_vars` is the number of
variables (vector dimensions) and `n_obs` the number of
observations

Returns
-------
evals : array
sorted eigenvalues
evecs : array
sorted eigenvectors
score : array
projection of the data on `ncomps` components
"""

    #norm=data/np.std(data,1)[:,np.newaxis]
    #norm[np.isnan(norm)]=0
    #norm = data
    data = data.astype(np.float64)
    K=np.cov(data)
    evals,evecs=np.linalg.eig(K)
    order=np.argsort(evals)[::-1]
    evecs=np.real(evecs[:,order])
    evals=np.abs(evals[order])
    score= np.dot(evecs[:,:ncomps].T,data)
    score = score/np.sqrt(evals[:ncomps, np.newaxis])
    return evals,evecs,score